Alberto Bosio
YOU?
Author Swipe
View article: CTNI-04. A PHASE 1, FIRST-IN-HUMAN STUDY OF REGORAFENIB PLUS TEMOZOLOMIDE WITH OR WITHOUT RADIOTHERAPY IN PATIENTS WITH NEWLY DIAGNOSED MGMT METHYLATED, IDH WILDTYPE GLIOBLASTOMA: THE REGOMA-2 TRIAL
CTNI-04. A PHASE 1, FIRST-IN-HUMAN STUDY OF REGORAFENIB PLUS TEMOZOLOMIDE WITH OR WITHOUT RADIOTHERAPY IN PATIENTS WITH NEWLY DIAGNOSED MGMT METHYLATED, IDH WILDTYPE GLIOBLASTOMA: THE REGOMA-2 TRIAL Open
BACKGROUND Regorafenib (REG) is an oral multikinase inhibitor that has shown synergistic antitumor effects with radiotherapy and temozolomide (TMZ) in glioblastoma. This phase 1 study evaluated the safety, dose-limiting toxicity (DLT), max…
P14.27.B LONG-TERM OUTCOMES AND MOLECULARLY-GUIDED MANAGEMENT OF ADULT MEDULLOBLASTOMA: DATA FROM A SINGLE-INSTITUTION EXPERIENCE Open
BACKGROUND Medulloblastoma(MB) is an exceedingly rare malignancy in adults, with limited prospective data guiding its management. Although multimodal treatment remains the standard, recent molecular profiling has enabled the introduction o…
A Counterfactual Reasoning Framework for Fault Diagnosis in Robot Perception Systems Open
Perception systems provide a rich understanding of the environment for autonomous systems, shaping decisions in all downstream modules. Hence, accurate detection and isolation of faults in perception systems is important. Faults in percept…
Closing the Loop Inside Neural Networks: Causality-Guided Layer Adaptation for Fault Recovery Control Open
This paper studies the problem of real-time fault recovery control for nonlinear control-affine systems subject to actuator loss of effectiveness faults and external disturbances. We derive a two-stage framework that combines causal infere…
A Genetic Approach for Automatic AxC Design Exploration at RTL Based on Assertion Mining and Fault Analysis Open
International audience
Reliability-Aware Hyperparameter Optimization for ANN-to-SNN Conversion Open
Spiking Neural Networks (SNNs) have emerged as an energy-efficient alternative to Artificial Neural Networks (ANNs), particularly for edge-computing and safety-critical applications. Unlike conventional ANNs, SNNs leverage sparse event-dri…
Automatic generation of input-aware approximate arithmetic circuits Open
International audience
A Survey on Design Space Exploration Approaches for Approximate Computing Systems Open
Approximate Computing (AxC) has emerged as a promising paradigm to enhance performance and energy efficiency by allowing a controlled trade-off between accuracy and resource consumption. It is extensively adopted across various abstraction…
Reliable and Efficient hardware for Trustworthy Deep Neural Networks Open
International audience
A Survey on Design Space Exploration Approaches for Approximate Computing Systems Open
Approximate Computing (AxC) has emerged as a promising paradigm to enhance performance and energy efficiency by allowing a controlled trade-off between accuracy and resource consumption. It is extensively adopted across various abstraction…
3D VNWFET-Based Standard Cell Library Design Flow: from Circuit and Physical Design to Logic Synthesis Open
International audience
The impact of feature representation on the accuracy of photonic neural networks Open
Photonic neural networks (PNNs) are gaining significant interest in the research community due to their potential for high parallelization, low latency, and energy efficiency. PNNs compute using light, which leads to several differences in…
VNWFET-Based Systolic Array Accelerator for Deep Neural Networks Open
International audience
Hardware Accelerator for FIPS 202 Hash Functions in Post-Quantum Ready SoCs Open
International audience
The Impact of Feature Representation on the Accuracy of Photonic Neural Networks Open
Photonic Neural Networks (PNNs) are gaining significant interest in the research community due to their potential for high parallelization, low latency, and energy efficiency. PNNs compute using light, which leads to several differences in…
Deploying Compact and Dependable DNNs in Safety-critical Applications Open
National audience
Approximate Fault-Tolerant Neural Network Systems Open
International audience
View article: Special Session: Reliability Assessment Recipes for DNN Accelerators
Special Session: Reliability Assessment Recipes for DNN Accelerators Open
Reliability assessment is mandatory to guarantee the correct behavior of Deep Neural Network (DNN) hardware accelerators in safety-critical applications. While fault injection stands out as a well-established, practical and robust method f…
SAFFIRA: a Framework for Assessing the Reliability of Systolic-Array-Based DNN Accelerators Open
International audience
View article: FVLLMONTI: The 3D Neural Network Compute Cube $(N^{2}C^{2})$ Concept for Efficient Transformer Architectures Towards Speech-to-Speech Translation
FVLLMONTI: The 3D Neural Network Compute Cube $(N^{2}C^{2})$ Concept for Efficient Transformer Architectures Towards Speech-to-Speech Translation Open
International audience
High-Performance Data Mapping for BNNs on PCM-Based Integrated Photonics Open
International audience
SAFFIRA: a Framework for Assessing the Reliability of Systolic-Array-Based DNN Accelerators Open
Systolic array has emerged as a prominent architecture for Deep Neural Network (DNN) hardware accelerators, providing high-throughput and low-latency performance essential for deploying DNNs across diverse applications. However, when used …
High-Performance Data Mapping for BNNs on PCM-based Integrated Photonics Open
State-of-the-Art (SotA) hardware implementations of Deep Neural Networks (DNNs) incur high latencies and costs. Binary Neural Networks (BNNs) are potential alternative solutions to realize faster implementations without losing accuracy. In…
Energy-efficient Computation-In-Memory Architecture using Emerging Technologies Open
International audience
Exploring the bandwidth-limited readout in coherent photonic reservoir computing Open
International audience